道德对齐之上的伦理推理：LLMs中上下文伦理策略的案例与框架
Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs
AI总结：
本文提出用通用伦理推理能力替代道德对齐，开发整合道德困境与原则的框架，实验显示GPT-4近乎完美但仍有西方价值观偏见。
摘要：
在这篇立场论文中，我们认为与其将LLMs道德对齐到特定的伦理原则集，不如向其注入通用的伦理推理能力，以便它们能够在全球范围内处理价值多元主义。当提供一个伦理策略时，LLM应能够做出与该策略伦理一致的决策。我们开发了一个框架，将道德困境与涉及不同规范伦理学形式主义、不同抽象层次的道德原则相结合。使用GPT-x模型的初步实验表明，虽然GPT-4几乎是一个完美的伦理推理者，但模型仍然偏向于西方和英语社会的道德价值观。
英文摘要：
In this position paper, we argue that instead of morally aligning LLMs to specific set of ethical principles, we should infuse generic ethical reasoning capabilities into them so that they can handle value pluralism at a global scale. When provided with an ethical policy, an LLM should be capable of making decisions that are ethically consistent to the policy. We develop a framework that integrates moral dilemmas with moral principles pertaining to different foramlisms of normative ethics, and at different levels of abstractions. Initial experiments with GPT-x models shows that while GPT-4 is a nearly perfect ethical reasoner, the models still have bias towards the moral values of Western and English speaking societies.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
